Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0311. Min Range: -6.0311
Max Act: 6.0311. Min Act: -0.1700
Data Index: 7721049 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.8748. Min Act: -0.1700
Data Index: 5552031 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.8436. Min Act: -0.1700
Data Index: 3831756 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7811. Min Act: -0.1700
Data Index: 4423569 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.8123. Min Act: -0.1700
Data Index: 1300634 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.8123. Min Act: -0.1700
Data Index: 1019179 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.8436. Min Act: -0.1700
Data Index: 4573844 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.8436. Min Act: -0.1700
Data Index: 7754985 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7811. Min Act: -0.1700
Data Index: 8753581 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7811. Min Act: -0.1700
Data Index: 6261093 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7498. Min Act: -0.1700
Data Index: 5616303 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2564368 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2420644 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7498. Min Act: -0.1700
Data Index: 1100279 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7186. Min Act: -0.1700
Data Index: 5938428 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.7186. Min Act: -0.1700
Data Index: 5698378 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.6873. Min Act: -0.1700
Data Index: 4042876 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.6873. Min Act: -0.1700
Data Index: 4839316 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.6873. Min Act: -0.1700
Data Index: 379525 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0311. Min Range: -6.0311
Max Act: 5.6873. Min Act: -0.1700
Data Index: 4649020 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19